利用改进的BP神经网络,以钢纤雏混凝土的分离式霍普金森压杆试验数据为训练样本,建立了钢纤维混凝土的隐式动态本构模型。以显式动态有限元软件ABAQUS/Explicit为开发平台,采用FORTRAN语言编写了材料用户子程序VUMAT,将神经网络表达的材料动态本构模型嵌入到有限元计算中,实现了冲击荷载下钢纤维混凝土结构响应的数值模拟。算例显示,建立的本构模型和相应的有限元方法是有效的。
Taking the split Hopkinson pressure bar(SHPB) test data as training samples, an implicit dynamic constitutive model of steel fiber reinforced concrete(SFRC) was proposed with the improved BP neural network program. On the basis of ABAQUS/Explieit, a user-defined material subroutine VUMAT was compiled with FORTRAN language, embedding with the neural network constitutive model into finite element calculation. With SFRC structure's response under impact load as ease study, it is shown that the constructed constitutive model and its finite element method are effective.